© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 25506
    Prev
    Next
    INDEX
    Explanations

    interactions involving authority and resistance to pressure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Juliushanhanhan/llama-3-8b-it-res/blocks.25.hook_resid_post
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    gated
    Context Size
    1,024
    Dataset
    Juliushanhanhan/openwebtext-1b-llama3-tokenized-cxt-1024
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itan
    -0.15
    alse
    -0.14
    rets
    -0.14
    ALSE
    -0.14
     Flags
    -0.14
     ìķħ
    -0.14
    anch
    -0.14
    ito
    -0.14
     Tits
    -0.13
    794
    -0.13
    POSITIVE LOGITS
     dict
    0.31
     imposition
    0.28
    dict
    0.28
     Dict
    0.27
     boss
    0.26
     bullying
    0.26
    Dict
    0.26
     steam
    0.26
     lect
    0.25
     impose
    0.25
    Activations Density 0.051%

    No Known Activations